4 citations · 7 across the 9 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2024
Proper Latent Decomposition
Daniel Kelshaw, Luca Magri
In this paper, we introduce the proper latent decomposition (PLD) as a generalization of the proper orthogonal decomposition (POD) on manifolds. PLD is a nonlinear reduced-order mo…
cs.LG2024
Computing distances and means on manifolds with a metric-constrained Eikonal approach
Daniel Kelshaw, Luca Magri
Computing distances on Riemannian manifolds is a challenging problem with numerous applications, from physics, through statistics, to machine learning. In this paper, we introduce…
cs.LG2023
Short and Straight: Geodesics on Differentiable Manifolds
Daniel Kelshaw, Luca Magri
Manifolds discovered by machine learning models provide a compact representation of the underlying data. Geodesics on these manifolds define locally length-minimising curves and pr…